{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:G2B7EK2JAM5ALPV434QWSP5EMO","short_pith_number":"pith:G2B7EK2J","schema_version":"1.0","canonical_sha256":"3683f22b49033a05bebcdf21693fa463a50ea671f48adc969f3e65016b82e13e","source":{"kind":"arxiv","id":"1902.04208","version":5},"attestation_state":"computed","paper":{"title":"MaCow: Masked Convolutional Generative Flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Eduard Hovy, Shanghang Zhang, Xiang Kong, Xuezhe Ma","submitted_at":"2019-02-12T01:31:06Z","abstract_excerpt":"Flow-based generative models, conceptually attractive due to tractability of both the exact log-likelihood computation and latent-variable inference, and efficiency of both training and sampling, has led to a number of impressive empirical successes and spawned many advanced variants and theoretical investigations. Despite their computational efficiency, the density estimation performance of flow-based generative models significantly falls behind those of state-of-the-art autoregressive models. In this work, we introduce masked convolutional generative flow (MaCow), a simple yet effective arch"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1902.04208","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-12T01:31:06Z","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"title_canon_sha256":"85830d8a7475dffa4141da3ff5460cba1034f64a277ca210d2ddd597480aad96","abstract_canon_sha256":"42ea13c59cf4b16eec68b51bd17d43029d89acc3a0cf912796f4f2cd446ace12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:15:02.845986Z","signature_b64":"HusdjfXUpv3457XyZiNO9qbje0Jw/IvFbLajEGns5wTNe1YX2YFhNReoIVvq9T6h9KAnwaH12nqychLeU/j1BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3683f22b49033a05bebcdf21693fa463a50ea671f48adc969f3e65016b82e13e","last_reissued_at":"2026-07-05T00:15:02.845442Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:15:02.845442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MaCow: Masked Convolutional Generative Flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Eduard Hovy, Shanghang Zhang, Xiang Kong, Xuezhe Ma","submitted_at":"2019-02-12T01:31:06Z","abstract_excerpt":"Flow-based generative models, conceptually attractive due to tractability of both the exact log-likelihood computation and latent-variable inference, and efficiency of both training and sampling, has led to a number of impressive empirical successes and spawned many advanced variants and theoretical investigations. Despite their computational efficiency, the density estimation performance of flow-based generative models significantly falls behind those of state-of-the-art autoregressive models. In this work, we introduce masked convolutional generative flow (MaCow), a simple yet effective arch"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.04208","kind":"arxiv","version":5},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1902.04208/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1902.04208","created_at":"2026-07-05T00:15:02.845499+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.04208v5","created_at":"2026-07-05T00:15:02.845499+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.04208","created_at":"2026-07-05T00:15:02.845499+00:00"},{"alias_kind":"pith_short_12","alias_value":"G2B7EK2JAM5A","created_at":"2026-07-05T00:15:02.845499+00:00"},{"alias_kind":"pith_short_16","alias_value":"G2B7EK2JAM5ALPV4","created_at":"2026-07-05T00:15:02.845499+00:00"},{"alias_kind":"pith_short_8","alias_value":"G2B7EK2J","created_at":"2026-07-05T00:15:02.845499+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1909.02480","citing_title":"FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G2B7EK2JAM5ALPV434QWSP5EMO","json":"https://pith.science/pith/G2B7EK2JAM5ALPV434QWSP5EMO.json","graph_json":"https://pith.science/api/pith-number/G2B7EK2JAM5ALPV434QWSP5EMO/graph.json","events_json":"https://pith.science/api/pith-number/G2B7EK2JAM5ALPV434QWSP5EMO/events.json","paper":"https://pith.science/paper/G2B7EK2J"},"agent_actions":{"view_html":"https://pith.science/pith/G2B7EK2JAM5ALPV434QWSP5EMO","download_json":"https://pith.science/pith/G2B7EK2JAM5ALPV434QWSP5EMO.json","view_paper":"https://pith.science/paper/G2B7EK2J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.04208&json=true","fetch_graph":"https://pith.science/api/pith-number/G2B7EK2JAM5ALPV434QWSP5EMO/graph.json","fetch_events":"https://pith.science/api/pith-number/G2B7EK2JAM5ALPV434QWSP5EMO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G2B7EK2JAM5ALPV434QWSP5EMO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G2B7EK2JAM5ALPV434QWSP5EMO/action/storage_attestation","attest_author":"https://pith.science/pith/G2B7EK2JAM5ALPV434QWSP5EMO/action/author_attestation","sign_citation":"https://pith.science/pith/G2B7EK2JAM5ALPV434QWSP5EMO/action/citation_signature","submit_replication":"https://pith.science/pith/G2B7EK2JAM5ALPV434QWSP5EMO/action/replication_record"}},"created_at":"2026-07-05T00:15:02.845499+00:00","updated_at":"2026-07-05T00:15:02.845499+00:00"}